China
Africa
Explore chapters and articles related to this topic
Multimodal Ambulatory Fall Risk Assessment in the Era of Big Data
Published in Ervin Sejdić, Tiago H. Falk, Signal Processing and Machine Learning for Biomedical Big Data, 2018
Optical motion capture: In laboratory settings, 3-D optical motion capture systems allow the derivation of spatiotemporal gait variables by tracking markers attached to body landmarks. In popular systems, such as CODA6 [34] or Vicon (Vicon Ind., Oxford, UK), multiple optical sensors track body-worn markers and calculate position based on localization techniques to estimate the movement kinematics. Variables, such as joint angles, step length, and toe clearance, are calculated and can be displayed in real time. Limitations of motion capture systems are the requirement to wear markers on the body, limited working volumes, and stringent calibration requirements. The complexity and high cost of these systems limit them mainly to research purposes.
Wearable Communication and Medical Systems
Published in Albert Sabban, Novel Wearable Antennas for Communication and Medical Systems, 2017
Gait analysis based on wearable devices can be applied in healthcare monitoring, such as in the detection of gait abnormalities, the assessment of recovery, fall risk estimation, and in sports training. In healthcare centers, gait information is used to detect walking behavior abnormalities that may predict health problems or the progression of neurodegenerative diseases. Falling is the most common type of home accident among elderly persons. It is a major threat to the health and independence among elderly people. Gait analysis using wearable devices has been used to analyze and predict falls among elderly patients.
Wearable Technologies for 5G, Medical and Sport Applications
Published in Albert Sabban, Wearable Systems and Antennas Technologies for 5G, IOT and Medical Systems, 2020
Gait analysis based on wearable devices may be applied in healthcare monitoring, such as in the detection of gait abnormalities, the assessment of recovery, fall risk estimation and in sport training. In healthcare centers, gait information is used to detect walking behavior abnormalities that may predict health problems or the progression of neurodegenerative diseases. Fall is the most common type of home accident among elderly people. Falls are a major threat to health and independence among elderly people. Gait analysis using wearable devices was used to analyze and predict fall among elderly patients [40–44].
Using Skeleton Correction to Improve Flash Lidar-based Gait Recognition
Published in Applied Artificial Intelligence, 2022
Nasrin Sadeghzadehyazdi, Tamal Batabyal, Alexander Glandon, Nibir Dhar, Babajide Familoni, Khan Iftekharuddin, Scott T. Acton
The problem of gait identification has received significant interest in the last decade due to the various applications in areas ranging from intelligent security surveillance and identifying persons of interest in criminal cases to designated smart environments (Charalambous 2014; Jain, Bolle, and Pankanti 2006). Gait analysis also plays an important role in quantifying the severity of certain motion-related diseases such as Parkinson’s disease (Din, Silvia, and Rochester 2016). While the iris (Daugman 2009), face (Schroff, Kalenichenko, and Philbin 2015), and fingerprint (Maltoni et al. 2009) provide some of the most robust biometrics for person identification, they require the cooperation of subjects as well as the availability of high-quality data. However, many scenarios exist in which the subjects cannot be controlled or acquisition of data is impossible. Under such circumstances, biometrics that can be extracted from gait have shown promising results in several studies (Preis et al. 2012; Sinha, Chakravarty, and Bhowmick 2013). Features extracted from gait are resilient to changes in clothing or lighting conditions compared to color or texture, which are among the prevalent features for person identification. While patterns of walking may not be necessarily unique to individuals in practice, a combination of biometric-based static attributes, along with motion analysis of certain body joints, can create an effective set of features to recognize an individual.
Dimensional reduction of balance parameters in risk of falling evaluation using a minimal number of force-sensitive resistors
Published in International Journal of Occupational Safety and Ergonomics, 2022
Johannes C. Ayena, Martin J.-D. Otis
We hold the opinion that reducing the number of sensors in an instrumented insole will help to reduce the manufacturing cost, power consumption and embedded memory size. Also, this can improve the physical integration of sensors and electronics packaging. We also think that the ROFA index computed with minimal gait and balance parameters should allow the clinician to better identify the patient at ROFA. The ROFA index with the reduced set of parameters is computed by our instrumented insole [58] and can be transmitted wirelessly to a mobile device. In this case, the information displayed on the mobile device can be understood easily by clinicians and patients. This monitoring is important to assess the progression of disease related to gait disorders and the improvement between clinical visits. In addition, it can give information to the neurologist to adjust drug prescriptions as needed. The longitudinal change information is important for rehabilitation and probably can help to decrease the number of visits to physicians and clinicians. The collected data will be useful for extracting some information in real time to suggest a correction in regard of gait deficits and some other motor complications, like motor fluctuations.
Role of machine learning in gait analysis: a review
Published in Journal of Medical Engineering & Technology, 2020
A great need is to make the journey from offline analysis, i.e., laboratory-based experiments to real-time scenarios, i.e., clinician’s efficient intelligent tools. A much needful is required to deal with patients’ gait rather than normal gait though a basic understanding will pave way for abnormality detection. The generalisation of the model with different conditions, more population size, and transfer learning approach is needed, as this model once trained can be used on patients with similar impairments [37]. The ambitious application areas for gait analysis such as prediction of onset of diseases, the progression of the disease, rehabilitation rates and planning trajectories identical to human natural gait for controlling rehabilitation devices will get benefitted using AI in near future. However, technology development has proven useful by providing portability, continuous monitoring and cost-effective solution to gait study domains by the development of sensor-based approaches. The development of these approaches requires long-term data collection, monitoring of patient state, determining rehabilitation modules, and systematic data storage for training and validation of learning techniques. However, these techniques may possibly be applicable as assisting devices for physicians in clinical diagnosis and control of gait rehabilitation devices that can help physiotherapists in therapeutic interventions being adaptive to different conditions and entails different gait pathologies.